New ITAGAKI interview touches on 360 and PS3 comparison

[expletive]

As Titanio says, parallelism isn tthe issue. XB360 has that same issue. Plus the SPE's can be written for C/C++, unlike PS2's VU's that were assembler only. PS3's in order, as is XB360, as is PS2, so in that instance PS3 is no worse off then PS2 or XB360 either.
The only fundamental 'difficulty' of PS3 over XB360 is working in 256kb LS's and managing data structures to fit that.
You're another of these 'STI wasted buckets of money on a useless and overly difficult design' subscribers I see! We've no real world gaming examples, but we HAVE seen the advantages of Cell demo's over other processors, and we HAVE seen where the SPE's architecture has benefits.

Regardless of the actual hardware benefits, a lot of developers who prefer the 360 have commented on the overall dev environment and the tools they can use. Debuggers, performance tools, etc. Plus they are all tools that developers who develop for the PC are familiar with already and those who havent, claim they are easy to use. (and after seeing the pc version of the 360 controller, its obvious this is a HUGE part of MS' mid to long-term strategy: one development budget-two platforms)

That said, paralleism with 3 identical cores and 6 identical threads should be a bit easier than a PPE and SPE design where each has different needs and potentially different roles shouldnt it? (I have to credit that thought to Carmack though, as he stated in his Quakecon address.)

What we have not seen, however, is if the Cell will provide an advantage in the closed-box system known as the PS3 and i think thats what is really on trial in this thread.

J

 

[darkblu]

That said, paralleism with 3 identical cores and 6 identical threads should be a bit easier than a PPE and SPE design where each has different needs and potentially different roles shouldnt it? (I have to credit that thought to Carmack though, as he stated in his Quakecon address.)

i'm not aware of the exact words of Carmack but no, 'parallelism with 3 identical cores and 6 identical threads' would not be necesserily easier than the ps3 model due to a number or different reasons. but of course that's yet to be determined in practice.

 

[Josh378]

I'm not a fan of his fighting games...but ITAGAKI and his team can create a great action/fighter game....(although you'll be seeing alot of "patches" in the future).

I really want him to step away from Just eye-candy only and really put a focus on a complex fighting engine...I would love to see the speed of DoA4 with Virtual Fighter techniques (dreams). But seriously, look at Xbox's fighting games on the system....only 2 really stand out (DOA and Soul Calibur)

On PS2 it's about 5-15 great fighting games on the system. He made the right choice on system solutions with xbox vs PS2...xbox will just give him better sales and reconition. On the other hand...the Action/Adventure Genre is wide open for him to take...but it does have Hard competition like DMC and GoW...but not asbad as the fighter genre. Ninja Gaiden will stand out more in it's role on PS3 than DoA would be on PS3...thats why I say...let his fighters be Xbox 360 exclusive and then make NG Black on Xbox 360 and port it to PS3 with Downloadable patches/updates......

Now, i'm off to finish Metroid Prime 2...

 

[MechanizedDeath]

Itagaki speaks his mind, period. That quote said nothing about power for or against either machine. This thread is unnecessarily long. PEACE.

 

[zRifle1z]

Itagaki speaks his mind, period. That quote said nothing about power for or against either machine. This thread is unnecessarily long. PEACE.

This thread unfortunately overlooks this statement as well:

"GI: Visually, what do you feel that you could accomplish with the Xbox 360 that you couldn’t with the Xbox? I’ve played Ultimate and DOA 3 on an HDTV and it already looked fantastic.

Itagaki: What you see is what you get. I never felt that I had enough machine power. The more power I get the more I want to do. Even with Xbox 360 there’s never enough. I must tell you an interesting story since you came all the way to Tokyo for me. Of course, as a developer we welcome more power. From a consumer stand point, they must feel that there’s already enough power. Back in 1997 – 8 years ago – I made games. I look back and I surprise myself. I’m impressed with what I see and what I did 8 years ago. Eight years from today I don’t think I’m going to look back at today and feel as impressed as I feel about product from 8 years ago. So of course, for the last 8 years, our focus was to improve the graphics quality, and of course without having enough power, that became a challenge. From this point forward, obviously that won’t be the focus, and we’ll be working more on interactivity – things like this lobby – more about the actual game concept and gameplay. That’s where I think my focus will be on.

 

[expletive]

i'm not aware of the exact words of Carmack but no, 'parallelism with 3 identical cores and 6 identical threads' would not be necesserily easier than the ps3 model due to a number or different reasons. but of course that's yet to be determined in practice.

"So the returns on multi-core are going to be initially disappointing, for developers or for what people get out of it. There are decisions that the hardware makers can choose on here that make it easier or harder. And this is a useful comparison between the xbox 360 and what we’ll have on the PC spaces and what we’ve got on the PS3.

The xbox 360 has an architecture where you’ve essentially got three processors and they’re all running from the same memory pool and they’re synchronized and cache coherent and you can just spawn off another thread right in your program and have it go do some work.

Now that’s kind of the best case and it’s still really difficult to actually get this to turn into faster performance or even getting more stuff done in a game title. "

There as another interview where he specifically mentions identical cores but i cant seem to track it down.

I dont know of another developer at his level that has said otherwise. I'd be interested to see any who disagree with this statement becuase it seems to make perfect sense.

J

 

[dantruon]

Just because Cell has double the FP power of XeCPU, doesn't mean PS3 the system is more powerful than x360.

ahhahah, you being sarcastic right?

I think the reason that Techmo doesnt want to develop DOA to playstation platform in general is because they will have to compete with Tekken and Virtual Fighter and I dont think they can beat those two games in term of sale, but if they develop for MS, they are like monopoly on that platform, so in my opinion that is one of the main factor we will never see the DOA series on the PS3, but Ninja Gaider might have a chance though.

 

[darkblu]

"The xbox 360 has an architecture where you’ve essentially got three processors and they’re all running from the same memory pool and they’re synchronized and cache coherent and you can just spawn off another thread right in your program and have it go do some work.

Now that’s kind of the best case and it’s still really difficult to actually get this to turn into faster performance or even getting more stuff done in a game title. "

I dont know of another developer at his level that has said otherwise. I'd be interested to see any who disagree with this statement becuase it seems to make perfect sense.

regardless of how true his statement is in itself, the question is: what do _you_ read into his statement.

the first paragraph of Carmack's statement basically says: 'it is very easy to spawn a thread and get it running on the 360 - just as easy as it is on your grandma's smp pc'

to which eveybody can only nod in agreement, as there's nothing to misundersand here and that message gets clearly and correctly propagated. now, getting a thread up and running and actually getting efficient parallelism are two entirely different things, as anybody who has ever tackled a single parallelism problem could tell you. so let's see what Carmack says further in his second paragraph.. he says exactly this - 'regardless of how easy it's to tinker with threads (in your grandma's smp way) this still grants you nothing in terms of effective paralellism'.

ok, now that we cleared up the matter with Carmack's statement we can return to the original topic - how much easier it is to achieve _efficient_parallelism_ on the 360 over the cell. and now it's your turn to step in and actually build your argument.

 

[barnak]

lol funny quote I found on GA.

"Does anybody else find it slightly ironic that Itagaki is complaining about developing PS3 games because its too hard and yet he rags on people who find Ninja Gaiden too hard and calls them Ninja Dogs? Who's the ninja dog now Itagaki?"

 

[ecliptic]

lol funny quote I found on GA.

"Does anybody else find it slightly ironic that Itagaki is complaining about developing PS3 games because its too hard and yet he rags on people who find Ninja Gaiden too hard and calls them Ninja Dogs? Who's the ninja dog now Itagaki?"

That is suppose to be funny?

The idiot is comparing a developing a game to playing a game. Playing a game doesn't costs an extra $10 million because the game is harder than another game.

 

[liverkick]

That is suppose to be funny?

The idiot is comparing a developing a game to playing a game. Playing a game doesn't costs an extra $10 million because the game is harder than another game.

Yes its funny. Because its a joke. Jokes are meant to be funny and taken in jest. Not everything is a veiled indictment against your favorite brand. Calm down.

 

[jpr27]

Accert I agree with your first post made alot of good points.

I just hope that TN really polishes up their character detail. I agree with a previous poster about the characters (at this point so far) are not a huge departure then what we got in DOAU. Granted its a first generation launch title etc. but honestly I did expect a little more from TN especially given what they produced with the Xbox 1 launch. A little rough yeh but impressive for a first gen title on a new system.

 

[one]

Well it's at least near 60fps in 720p (though its animation and gameplay look almost the same as in the previous generation) so if it's that hard to get it on Xbox 360 then Itagaki shouldn't be blamed more than other devs shooting for 30fps...

http://www.gametrailers.com/player.php?id=7796&type=wmv
http://www.gametrailers.com/player.php?id=7797&type=wmv (HD)

 

[ihamoitc2005]

multiple cores

There as another interview where he specifically mentions identical cores but i cant seem to track it down.

I dont know what he said but 2 identical cores like SLI GPUs: 2x processing power, but real word much less, but with joint L2 cache can be more efficient than GPUs no? I think he says its not easy to be efficienct with multiple threads because of small cache.

SPEs very good at dynamic load balancing if data model is appropriate so full performance possible from all SPEs, do not have to write to any one SPE, only write SPE appropriate code.

Sony very smart in processor design but stupid in assuming developer adoption of recommended programming model. Sony said PS2 performance attainable if followed recommended model and in the end it was true. Same with CELL. Maybe we must wait 4 years before a lot of good CELL using games. Actually maybe much less this time since Sony is making better SDK.

Itagaki is making fun of other x360 developers no? Funny since DOA2 looks bad next to Virtua Fighter 4 & Tekken 5. Maybe PS2 too "complicated" for Itagaki. Not too complicated for Namco no?

 

[aaaaa00]

ok, now that we cleared up the matter with Carmack's statement we can return to the original topic - how much easier it is to achieve _efficient_parallelism_ on the 360 over the cell. and now it's your turn to step in and actually build your argument.

It's generally easier to write fast code when it's easier to write correct code, since fast but incorrect code is not typically very useful.

Correct multithreaded code is much easier to write when you have N identical CPUs all sharing identical access to the same main memory, with a well-ordered memory model and cache coherency guaranteed by the hardware. (Which is pretty much x86 SMP in a nutshell in fact.)

Such an architecture is fairly well understood today, and any college concurrent programming textbook will teach you the basics of synchronization objects and have parallel algorithms that work correctly and reasonably well on an SMP.

Each step away you take from such an architecture introduces stuff that makes it more complicated just to insure code correctness, never mind performance.

The point Carmack is making is that xbox 360 is already pretty much the best case scenario for multithreaded architectures -- but even there, insuring code correctness is going to be hard to do before you even start to think about making the performance better.

And if you look at his whole argument, including his example, you can see that this was the point that he was making.

The xbox 360 has an architecture where you’ve essentially got three processors and they’re all running from the same memory pool and they’re synchronized and cache coherent and you can just spawn off another thread right in your program and have it go do some work.

Now that’s kind of the best case and it’s still really difficult to actually get this to turn into faster performance or even getting more stuff done in a game title.

The obvious architecture that you wind up doing is you try to split off the renderer into another thread. Quake 3 supported dual processor acceleration like this off and on throughout the various versions.

It’s actually a pretty good case in point there, where when we released it, certainly on my test system, you could run and get maybe a 40% speed up in some cases, running in dual processor mode, but through no changing of the code on our part, just in differences as video card drivers revved and systems changed and people moved to different OS revs, that dual processor acceleration came and went, came and went multiple times.

At one point we went to go back and try to get it to work, and we could only make it work on one system. We had no idea what was even the difference between these two systems. It worked on one and not on the other. A lot of that is operating system and driver related issues which will be better on the console, but it does still highlight the point that parallel programming, when you do it like this, is more difficult.

Anything that makes the game development process more difficult is not a terribly good thing.

 

[aaronspink]

As Titanio says, parallelism isn tthe issue. XB360 has that same issue. Plus the SPE's can be written for C/C++, unlike PS2's VU's that were assembler only. PS3's in order, as is XB360, as is PS2, so in that instance PS3 is no worse off then PS2 or XB360 either.

C/C++ could be used to program the VU's as well, its called intrinics, and anyone using C/C++ for the SPUs and getting any performance will be writting in a version of C just above macro assembler

The only fundamental 'difficulty' of PS3 over XB360 is working in 256kb LS's and managing data structures to fit that.

and the lack of direct memory access, etc.

I'd like to know what you think is so very difficult about PS3 versus XB360, 'coz I'm not seeing it, other than the SPE coding model which is something any capable coder can learn to work with without too much bother I'd have thought. Especially an (allegedly) self-proclaimed coding God like Itagaki

Um, I think you are underestimating the complexity of the cell programming model. It is significantly different enough from most architectures that it will remain a specialized field, some of those programmers will do a good job, but that will only be after a steep learning curve. The programming model for Xenon will be much more mainstream and already well researched with a significant amount of development funds spent. You also can't underestimate the amount of skill that will be spent at tackling any remaining issues with the x360 model because of the simularities with the more mainstream PC model.

Aaron Spink
speaking for myself inc.

 

[ihamoitc2005]

Spe Dma

and the lack of direct memory access, etc.

This is from IBM. Seems DMA no problem no?

http://www-128.ibm.com/developerworks/power/library/pa-cbea.html

SPEs access main storage with DMA commands that go between main storage and a private local memory used to store both instructions and data. SPE instruction- fetches and load and store instructions access this private local store rather than shared main storage.

This three-level organization of storage (register file, local store, main storage) -- with asynchronous DMA transfers between local store and main storage -- is a radical break with conventional architecture and programming models because it explicitly parallelizes computation and the transfers of data and instructions.

The reason for this radical change is that memory latency, measured in processor cycles, has gone up several hundredfold in the last 20 years. The result is that application performance is often limited by memory latency rather than peak compute capability or peak bandwidth. When a sequential program on a conventional architecture performs a load instruction that misses in the caches, program execution now comes to a halt for several hundred cycles. Compared with this penalty, the few cycles it takes to set up a DMA transfer for an SPE is quite small. Even with deep and costly speculation, conventional processors manage to get at best a handful of independent memory accesses in flight. The result can be compared to a bucket brigade in which a hundred people are required to cover the distance to the water needed to put the fire out, but only a few buckets are available.

In contrast, the explicit DMA model allows each SPE to have many concurrent memory accesses in flight without the need for speculation.

The most productive SPE memory-access model appears to be the one in which a list (such as a scatter-gather list) of DMA transfers is constructed in an SPE's local store so that the SPE's DMA controller can process the list asynchronously while the SPE operates on previously transferred data. In several cases, this new approach to accessing memory has led to application performance exceeding that of conventional processors by almost two orders of magnitude, significantly more than anyone would expect from the peak performance ratio (about 10x) between the Cell Broadband Engine and conventional PC processors.

 

[hugo]

The programming model for Xenon will be much more mainstream and already well researched with a significant amount of development funds spent. You also can't underestimate the amount of skill that will be spent at tackling any remaining issues with the x360 model because of the simularities with the more mainstream PC model.

Xenon isn't x86.I've never underestimated MS's software development skills but with Sony' recent move of going with software houses such as Epic and using Nvidia's CG tools,it shows that they indeed making efforts to make their console easier to develop for this coming gen.

 

[Gubbi]

This is from IBM. Seems DMA no problem no?

http://www-128.ibm.com/developerworks/power/library/pa-cbea.html

Of course they'll say that, the built the shite.

It's not that you explicitly have to set up a DMA that is the problem, it's that local stores aren't kept coherent. The lack of memory coherence *is* a bitch. The nuisance of the heterogenous ISA is minor compared to that.

Cheers
Gubbi

 

[ihamoitc2005]

SPE memory coherent

Of course they'll say that, the built the shite.

It's not that you explicitly have to set up a DMA that is the problem, it's that local stores aren't kept coherent. The lack of memory coherence *is* a bitch. The nuisance of the heterogenous ISA is minor compared to that.

Cheers
Gubbi

You didnt read the link.

It starts with ...

The Cell Broadband Engine is a single-chip multiprocessor with nine processors operating on a shared, coherent memory.

and

While each SPE is an independent processor running its own application programs, a shared, coherent memory and a rich set of DMA commands provide for seamless and efficient communications between all Cell processing elements.

Also referring to heterogeneous ISA ...

http://domino.research.ibm.com/comm/research.nsf/pages/r.arch.innovation.html?Open&printable

Memory access is performed via a DMA-based interface using copy-in/copy-out semantics, and data transfers can be initiated by either the IBM Powerâ„¢ processor or an SPU. The DMA-based interface uses the Power Architectureâ„¢ page protection model, giving a consistent interface to the system storage map for all processor structures despite its heterogeneous instruction set architecture structure.

Sounds pretty straightforward no?